专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

11. 发明授权

US07450758B2 Stylization of video 有权
标题翻译：视频风格化
公开(公告)号：US07450758B2
公开(公告)日：2008-11-11
申请号：US11942606
申请日：2007-11-19
申请人： Michael F. Cohen , Ying-Qing Xu , Heung-Yeung Shum , Jue Wang
发明人： Michael F. Cohen , Ying-Qing Xu , Heung-Yeung Shum , Jue Wang
IPC分类号： G06K9/00
CPC分类号： G11B27/034 , G06K9/00711 , G06T15/02 , H04N5/262
摘要： The techniques and mechanisms described herein are directed to a system for stylizing video, such as interactively transforming video to a cartoon-like style. Briefly stated, the techniques include determining a set of volumetric objects within a video, each volumetric object being a segment. Mean shift video segmentation may be used for this step. With that segmentation information, the technique further includes indicating on a limited number of keyframes of the video how segments should be merged into a semantic region. Finally, a contiguous volume is created by interpolating between keyframes by a mean shift constrained interpolation technique to propagate the semantic regions between keyframes.
摘要翻译：这里描述的技术和机制针对用于对视频进行风格化的系统，诸如将视频交互地变换成卡通样式。简而言之，技术包括确定视频内的一组体积对象，每个体积对象是一段。平均移位视频分割可用于该步骤。利用该分割信息，该技术还包括在片段的有限数量的关键帧上指示片段如何被合并到语义区域中。最后，通过平均偏移约束插值技术在关键帧之间进行内插以在关键帧之间传播语义区域来创建连续体积。

12. 发明授权

US07149329B2 Rapid computer modeling of faces for animation 有权
公开(公告)号：US07149329B2
公开(公告)日：2006-12-12
申请号：US10968553
申请日：2004-10-19
申请人： Zicheng Liu , Zhengyou Zhang , Michael F. Cohen , Charles E. Jacobs
发明人： Zicheng Liu , Zhengyou Zhang , Michael F. Cohen , Charles E. Jacobs
IPC分类号： G06K9/00
CPC分类号： G06T13/40 , G06K9/00201 , G06K9/00248 , G06K9/00268 , G06K9/00281 , G06T7/251 , G06T7/55 , G06T7/579 , G06T7/74 , G06T9/001 , G06T15/205 , G06T17/00 , G06T17/10 , G06T17/20 , G06T2200/08 , G06T2207/10012 , G06T2207/10016 , G06T2207/10021 , G06T2207/30201 , H04N19/162 , H04N19/503
摘要： Described herein is a technique for creating a 3D face model using images obtained from an inexpensive camera associated with a general-purpose computer. Two still images of the user are captured, and two video sequences. The user is asked to identify five facial features, which are used to calculate a mask and to perform fitting operations. Based on a comparison of the still images, deformation vectors are applied to a neutral face model to create the 3D model. The video sequences are used to create a texture map. The process of creating the texture map references the previously obtained 3D model to determine poses of the sequential video images.

13. 发明授权

US07082212B2 Rapid computer modeling of faces for animation 有权
公开(公告)号：US07082212B2
公开(公告)日：2006-07-25
申请号：US11048398
申请日：2005-02-01
申请人： Zicheng Liu , Zhengyou Zhang , Charles E. Jacobs , Michael F. Cohen
发明人： Zicheng Liu , Zhengyou Zhang , Charles E. Jacobs , Michael F. Cohen
IPC分类号： G06K9/00
CPC分类号： G06T13/40 , G06K9/00201 , G06K9/00248 , G06K9/00268 , G06K9/00281 , G06T7/251 , G06T7/55 , G06T7/579 , G06T7/74 , G06T9/001 , G06T15/205 , G06T17/00 , G06T17/10 , G06T17/20 , G06T2200/08 , G06T2207/10012 , G06T2207/10016 , G06T2207/10021 , G06T2207/30201 , H04N19/162 , H04N19/503
摘要： Described herein is a technique for creating a 3D face model using images obtained from an inexpensive camera associated with a general-purpose computer. Two still images of the user are captured, and two video sequences. The user is asked to identify five facial features, which are used to calculate a mask and to perform fitting operations. Based on a comparison of the still images, deformation vectors are applied to a neutral face model to create the 3D model. The video sequences are used to create a texture map. The process of creating the texture map references the previously obtained 3D model to determine poses of the sequential video images.

14. 发明授权

US07024279B2 Interpolation using radial basis functions with application to inverse kinematics 有权
公开(公告)号：US07024279B2
公开(公告)日：2006-04-04
申请号：US10875775
申请日：2004-06-24
申请人： Charles F. Rose, III , Peter-Pike J. Sloan , Michael F. Cohen
发明人： Charles F. Rose, III , Peter-Pike J. Sloan , Michael F. Cohen
IPC分类号： G06F19/00
CPC分类号： G06T13/40
摘要： A technique for solving an inverse-kinematic problem by interpolating solutions from examples. Example poses or motions of an object are collected and annotated. The annotations are essentially parameters for a function—i.e., the function X(p) generates degree-of-freedom values of an object that is posed in a manner that satisfies parameters p. The analytic function X is interpolated from these examples and improved automatically based on kinematic measurements. Preferably, the interpolation is created by taking a weighted sum of cardinal basis functions having linear and radial parts, Preferably, the interpolation is a weighted sum of cardinal basis functions having linear and radial portions.

15. 发明授权

US06950537B2 Rapid computer modeling of faces for animation 有权
公开(公告)号：US06950537B2
公开(公告)日：2005-09-27
申请号：US10846302
申请日：2004-05-14
申请人： Zicheng Liu , Zhengyou Zhang , Michael F. Cohen , Charles E. Jacobs
发明人： Zicheng Liu , Zhengyou Zhang , Michael F. Cohen , Charles E. Jacobs
IPC分类号： G06K9/00 , G06T13/40 , G06T15/20 , G06T17/00 , G06T17/10 , H04N7/26 , H04N7/36
CPC分类号： G06T13/40 , G06K9/00201 , G06K9/00248 , G06K9/00268 , G06K9/00281 , G06T7/251 , G06T7/55 , G06T7/579 , G06T7/74 , G06T9/001 , G06T15/205 , G06T17/00 , G06T17/10 , G06T17/20 , G06T2200/08 , G06T2207/10012 , G06T2207/10016 , G06T2207/10021 , G06T2207/30201 , H04N19/162 , H04N19/503
摘要： Described herein is a technique for creating a 3D face model using images obtained from an inexpensive camera associated with a general-purpose computer. Two still images of the user are captured, and two video sequences. The user is asked to identify five facial features, which are used to calculate a mask and to perform fitting operations. Based on a comparison of the still images, deformation vectors are applied to a neutral face model to create the 3D model. The video sequences are used to create a texture map. The process of creating the texture map references the previously obtained 3D model to determine poses of the sequential video images.

16. 发明授权

US06807290B2 Rapid computer modeling of faces for animation 有权
公开(公告)号：US06807290B2
公开(公告)日：2004-10-19
申请号：US09754938
申请日：2001-01-04
申请人： Zicheng Liu , Zhengyou Zhang , Michael F. Cohen , Charles E. Jacobs
发明人： Zicheng Liu , Zhengyou Zhang , Michael F. Cohen , Charles E. Jacobs
IPC分类号： G06K900
CPC分类号： G06T13/40 , G06K9/00201 , G06K9/00248 , G06K9/00268 , G06K9/00281 , G06T7/251 , G06T7/55 , G06T7/579 , G06T7/74 , G06T9/001 , G06T15/205 , G06T17/00 , G06T17/10 , G06T17/20 , G06T2200/08 , G06T2207/10012 , G06T2207/10016 , G06T2207/10021 , G06T2207/30201 , H04N19/162 , H04N19/503
摘要： Described herein is a technique for creating a 3D face model using images obtained from an inexpensive camera associated with a general-purpose computer. Two still images of the user are captured, and two video sequences. The user is asked to identify five facial features, which are used to calculate a mask and to perform fitting operations. Based on a comparison of the still images, deformation vectors are applied to a neutral face model to create the 3D model. The video sequences are used to create a texture map. The process of creating the texture map references the previously obtained 3D model to determine poses of the sequential video images.

17. 发明授权

US06466207B1 Real-time image rendering with layered depth images 失效
标题翻译：实时图像渲染与分层深度图像
公开(公告)号：US06466207B1
公开(公告)日：2002-10-15
申请号：US09040941
申请日：1998-03-18
申请人： Steven J. Gortler , Li-wei He , Michael F. Cohen
发明人： Steven J. Gortler , Li-wei He , Michael F. Cohen
IPC分类号： G06T1510
CPC分类号： G06T15/205
摘要： A method and computer product for rendering real-time three-dimensional images on a display based on view manipulation of prestored depth images in a global coordinate space. First, a layered depth image is generated from multiple depth images based on a predetermined display viewpoint. If the determined viewpoint is within a predetermined threshold of the layered depth image, the generated layered depth image is warped based on the determined display viewpoint, pixels from the layered depth image are splatted onto the warped image, and an output image is generated and displayed based on the splat pixels. If the determined viewpoint is outside the predetermined threshold of the previously generated layered depth image, a next closest layered depth image is generated. If the next closest layered depth image is not fully generated, the previously generated layered depth image is used to generate an output image. If the next closest layered depth image is fully generated, the process is repeated for the generated next closest layered depth image.
摘要翻译：一种用于基于在全局坐标空间中预先存储的深度图像的视图操纵在显示器上呈现实时三维图像的方法和计算机产品。首先，基于预定的显示视点从多个深度图像生成分层深度图像。如果所确定的视点在分层深度图像的预定阈值内，则基于所确定的显示视点来扭曲所生成的分层深度图像，并将来自分层深度图像的像素分解成弯曲图像，并且生成并显示输出图像基于splat像素。如果确定的视点在先前生成的分层深度图像的预定阈值之外，则生成下一个最接近的分层深度图像。如果未完全生成下一个最接近的分层深度图像，则使用先前生成的分层深度图像来生成输出图像。如果完全生成下一个最接近的分层深度图像，则对于生成的下一个最近的分层深度图像重复该过程。

18. 发明授权

US06462742B1 System and method for multi-dimensional motion interpolation using verbs and adverbs 有权
标题翻译：使用动词和副词进行多维运动插值的系统和方法
公开(公告)号：US06462742B1
公开(公告)日：2002-10-08
申请号：US09368750
申请日：1999-08-05
申请人： Charles F. Rose , Michael F. Cohen , Robert E. Bodenheimer, Jr.
发明人： Charles F. Rose , Michael F. Cohen , Robert E. Bodenheimer, Jr.
IPC分类号： G06T1300
CPC分类号： G06T13/40 , G06T2213/12
摘要： A system for providing improved computer animation can be used in interactive applications such as 3D video games and virtual environments. Tie system comprises an offline authoring system with tools for constructing controllable “verbs” from sets of motion example segments, and for constructing transitions between different verbs; and a runtime system for controlling the invocation of the verbs as parameterized by user defined “adverbs”. The system involves interpolating predefined animation segments created by an animator or through motion capture video. The animation segments are made up of data representing selected points on the animated creature (e.g., the joints and extremities) and values, as a function of time, for each degree of freedom of those points. In addition, a “verb graph” is constructed to act as the glue to assemble verbs and their adverbs into a runtime data structure. The verb graph defines the allowable transitions from one verb to another verb. A set of “keytimes” is also defined. The keytimes are instances when important structural events occur, and are used to pre-process the motion examples into a synchronized (canonical) time frame for interpolation.
摘要翻译：用于提供改进的计算机动画的系统可以用于诸如3D视频游戏和虚拟环境的交互式应用中。领带系统包括具有用于从运动示例段组合构建可控“动词”的工具的离线创作系统，以及用于构建不同动词之间的转换; 以及用于控制由用户定义的“副词”参数化的动词的调用的运行时系统。该系统涉及内插由动画制作者或通过运动捕捉视频创建的预定动画片段。动画片段由代表动画生物（例如关节和四肢）上的选定点的数据和作为时间的函数的值组成，用于这些点的每个自由度。另外，构造一个“动词图”，作为将动词及其副词组合成运行时数据结构的胶水。动词图定义了从一个动词到另一个动词的允许转换。还定义了一组“按键时间”。密钥时间是发生重要结构事件的情况，并且用于将运动示例预处理为用于插值的同步（规范）时间帧。

19. 发明授权

US06222937B1 Method and system for tracking vantage points from which pictures of an object have been taken 失效
标题翻译：跟踪已拍摄对象图片的有利位置的方法和系统
公开(公告)号：US06222937B1
公开(公告)日：2001-04-24
申请号：US08885251
申请日：1997-06-30
申请人： Michael F. Cohen , Radek Grzeszczuk
发明人： Michael F. Cohen , Radek Grzeszczuk
IPC分类号： G06K922
CPC分类号： G06T15/50 , G06T15/06
摘要： A computer-based method and system for digital 3-dimensional imaging of an object which allows for viewing images of the object from arbitrary vantage points. The system, referred to as the Lumigraph system, collects a complete appearance of either a synthetic or real object (or a scene), stores a representation of the appearance, and uses the representation to render images of the object from any vantage point. The appearance of an object is a collection of light rays that emanate from the object in all directions. The system stores the representation of the appearance as a set of coefficients of a 4-dimensional function, referred to as the Lumigraph function. From the Lumigraph function with these coefficients, the Lumigraph system can generate 2-dimensional images of the object from any vantage point. The Lumigraph system generates an image by evaluating the Lumigraph function to identify the intensity values of light rays that would emanate from the object to form the image. The Lumigraph system then combines these intensity values to form the image.
摘要翻译：一种用于对象的数字三维成像的基于计算机的方法和系统，其允许从任意有利位置观看对象的图像。称为Lumigraph系统的系统收集合成或实物（或场景）的完整外观，存储外观的表示，并使用该表示从任何优势点呈现对象的图像。物体的外观是从各个方向从物体发出的光线的集合。该系统将外观的表示存储为称为Lumigraph函数的四维函数的一组系数。从具有这些系数的Lumigraph函数，Lumigraph系统可以从任何有利位置生成对象的二维图像。 Lumigraph系统通过评估Lumigraph函数来生成图像，以识别从物体发出的形成图像的光线的强度值。然后，Lumigraph系统将这些强度值组合以形成图像。

20. 发明授权

US6023523A Method and system for digital plenoptic imaging 失效
标题翻译：数字全景成像方法与系统
公开(公告)号：US6023523A
公开(公告)日：2000-02-08
申请号：US885259
申请日：1997-06-30
申请人： Michael F. Cohen , Steven Gortler , Richard S. Szeliski
发明人： Michael F. Cohen , Steven Gortler , Richard S. Szeliski
IPC分类号： G06T15/06 , G06T15/50 , G06T15/00 , G06T17/00
CPC分类号： G06T15/50 , G06T15/06
摘要： A computer-based method and system for digital 3-dimensional imaging of an object which allows for viewing images of the object from arbitrary vantage points. The system, referred to as the Lumigraph system, collects a complete appearance of either a synthetic or real object (or a scene), stores a representation of the appearance, and uses the representation to render images of the object from any vantage point. The appearance of an object is a collection of light rays that emanate from the object in all directions. The system stores the representation of the appearance as a set of coefficients of a 4-dimensional function, referred to as the Lumigraph function. From the Lumigraph function with these coefficients, the Lumigraph system can generate 2-dimensional images of the object from any vantage point. The Lumigraph system generates an image by evaluating the Lumigraph function to identify the intensity values of light rays that would emanate from the object to form the image. The Lumigraph system then combines these intensity values to form the image.
摘要翻译：一种用于对象的数字三维成像的基于计算机的方法和系统，其允许从任意有利位置观看对象的图像。称为Lumigraph系统的系统收集合成或实物（或场景）的完整外观，存储外观的表示，并使用该表示从任何优势点呈现对象的图像。物体的外观是从各个方向从物体发出的光线的集合。该系统将外观的表示存储为称为Lumigraph函数的四维函数的一组系数。从具有这些系数的Lumigraph函数，Lumigraph系统可以从任何有利位置生成对象的二维图像。 Lumigraph系统通过评估Lumigraph函数来生成图像，以识别从物体发出的形成图像的光线的强度值。然后，Lumigraph系统将这些强度值组合以形成图像。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式